"Cursor Not Losing Memory or State" matching MCP connectors:

shared AI-context layer for teams — persistent memory your agents search and update over MCP

Publish websites from Claude, the terminal, or CI — drop a folder, get a link that doesn't expire.

RChilli MCP Hub is a production-grade MCP server that exposes RChilli's full HR data intelligence platform as 17 AI-callable tools across 4 categories. Built on 15+ years of HR data intelligence, it is trusted by ATS vendors, HR technology platforms, staffing agencies, and enterprise recruiting teams worldwide. Every tool is read-only and returns a consistent, structured JSON response — no raw exceptions, no inconsistent formats. Key Features Zero boilerplate — One endpoint, one OAuth login, 17 tools ready to use OAuth 2.1 + PKCE — No API keys to copy or paste; fully automatic auth flow 200+ resume fields — Name, contact, skills, experience, education, certifications, and taxonomy-enriched job profiles ONet / ESCO taxonomy — 10,000+ curated skills and job profiles with canonical mappings Explainable matching — Field-level evidence for every candidate-to-job score Bias redaction — PII and bias field removal for fair-hiring workflows Document conversion — PDF, DOCX, RTF, HTML — convert in any direction Auto-injected credentials — userkey and subuserid injected from token; never pass them manually Consistent response envelope — Every tool returns { success, data, meta } with trace ID and latency Use Cases Resume screening — Parse and structure resumes for AI-powered shortlisting Job description analysis — Extract required skills, experience range, and qualifications from any JD Candidate-to-job matching — One-to-one fit scoring with field-level evidence, no indexing required Talent pool search — Keyword search across your indexed resume database Skill gap analysis — Identify what a candidate is missing for a specific role Bias-free hiring — Redact names, photos, gender, and age before sharing with hiring managers Taxonomy enrichment — Look up and autocomplete 10,000+ standardized skills and job titles Document standardization — Convert and reformat candidate documents into consistent templates

AI-native form builder with a native MCP server. Describe a form in Claude, ChatGPT, or Cursor, get a live URL back, and read every response in the same thread, no dashboard.

Household finance memory, budgets, transactions, and monthly reviews for AI assistants.

Connect Claude, ChatGPT, Cursor, Gemini, and GitHub Copilot to your Onplana project portfolio. 27 tools (14 read, 13 write), OAuth 2.0 with Dynamic Client Registration, full audit trail.

Connect your AI to any database — PostgreSQL, MySQL, or SQL Server — in seconds.

Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.

An API for forecasting and multi-agent research. FutureSearch provides endpoints that use web research agents at scale, for higher accuracy than web search or single agent approaches alone can achieve. forecast runs a team of forecasters to predict future dates, numbers, and probabilities. multi_agent orchestrates multiple researchers to answer one question. agent_map runs one research agent over every row of a dataset, scaling to thousands of rows and agents.

MCP server for real-time product search by barcode (EAN, UPC, GTIN) or keyword on ean-search.org

SubDownload exposes YouTube as an MCP-native data source. Connect via OAuth and your AI agent can summarize videos, fetch full transcripts (even for videos with no captions, via AI ASR), search across channels, and save everything into a private knowledge base. Works with Claude, ChatGPT, Cursor, and 40+ MCP clients. Free credits on signup, no card required.

Privacy-first web analytics, exposed to your AI agent as a first-class data source. The agent sees your traffic, referrers, geos, devices, live visitors, and custom events, and can reason across them. Ask what changed since the last deploy, why a campaign underperformed, which segment of signups actually activated, or have it build a conversion funnel and alert you when bounce rate spikes.

Geolocate Me turns your phone into location context for any AI assistant. Install the iOS or Android app, connect once with OAuth, and your GPS is queryable in natural language. Ask where you are, where you parked, where you were yesterday at 3pm, or how long you were at the office — the assistant calls the tool and answers with a real street address. https://geolocateme.app

FFmpeg Micro MCP Server. Transcode videos from n8n or Make using FFmpeg in the cloud. Code+Docs: https://github.com/javidjamae/ffmpeg-micro-mcp/

Scraps Kitchen gives any AI agent a persistent, household-aware kitchen memory. Unlike generic chatbot recall, Scraps maintains structured cooking data: what's in your fridge (with freshness tracking), who you cook for (with allergens, dietary restrictions, and preferences), your recipe collection (with cook notes and per-diner ratings), your shopping list, and your kitchen equipment. 27 tools across 6 domains let agents read kitchen context, suggest meals that respect dietary safety, update the pantry after cooking, and build a history of what works for your household. Every interaction makes the data richer. Cooking history, preference signals, kitchen awareness = better suggestions next time. All tools work via oAuth and a free scraps.kitchen account.

A self-improving memory layer. Your memory, notes, tasks and goals, remembered everywhere.

Self-hosted MCP memory server for personal use and teams

An MCP server for deep research or task groups

Universal memory runtime for AI agents: episodic, semantic, and procedural memory with hybrid retrieval and spaced-repetition decay.

AI conversation memory that works everywhere. Save and recall conversations across Claude, ChatGPT, Gemini, Cursor, and all MCP-compatible platforms. 11 tools including semantic search, cross-platform discovery, shared community memories, and memory-powered workflows.